SkillsMCP serversHooks

tirth8205/code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

Stars
32,898
+7 days
—
Forks
2,993
Language
Python
License
MIT
Last push
16 Nov 2026

Summary

Summary written by AI from the README; it may be imprecise.

This tool builds a local knowledge graph of a codebase using Tree-sitter and stores code structure in SQLite. It provides an MCP server and CLI to supply AI coding assistants with targeted context, blast-radius analysis, and risk scoring during code reviews. Incremental updates via hooks or watch mode reparse only changed files.

Use it when

  • When conducting code reviews and needing to map impacted callers, dependencies, and test gaps
  • Serving compact, targeted codebase context to Claude Code or other AI assistants over MCP
  • Analyzing blast radius and change risk locally without sending source code to external services

Install

pip
uv tool install code-review-graph
pip
pip install -U code-review-graph
pip
pip install "code-review-graph[embeddings]"

Commands quoted from the repo's README. Read the README before running them.

Includes hooks that run shell commands on your machine. Read them before installing.

Needs a token or API key.

Stars over 90 days

Collecting: 2 of 90 days so far. The chart appears after 7 days.

Type to search the reference, templates and lessons.